bio-vcf 0.0.2 → 0.0.3

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.0.3

data/bin/bio-vcf

@@ -27,9 +27,34 @@ options = { show_help: false}
 opts = OptionParser.new do |o|
   o.banner = "Usage: #{File.basename($0)} [options] filename\ne.g.  #{File.basename($0)} < test/data/input/somaticsniper.vcf"
 
+  o.on('-i','--ignore-missing', 'Ignore missing data') do 
+    options[:ignore_missing] = true
+  end
   o.on('--filter cmd',String, 'Evaluate filter on each record') do |cmd|
     options[:filter] = cmd
   end
+
+  o.on('--sfilter cmd',String, 'Evaluate filter on each sample') do |cmd|
+    options[:sfilter] = cmd
+  end
+  o.on("--sfilter-samples list", Array, "Filter on selected samples") do |l|
+    options[:sfilter_samples] = l
+  end
+
+  o.on('--ifilter cmd','--if cmd',String, 'Include filter') do |cmd|
+    options[:ifilter] = cmd
+  end
+  o.on("--ifilter-samples list", Array, "Include set - implicitely defines exclude set") do |l|
+    options[:ifilter_samples] = l
+  end
+
+  o.on('--efilter cmd','--ef cmd',String, 'Exclude filter') do |cmd|
+    options[:efilter] = cmd
+  end
+  o.on("--efilter-samples list", Array, "Exclude set - overrides exclude set") do |l|
+    options[:efilter_samples] = l
+  end
+
   o.on('-e cmd', '--eval cmd',String, 'Evaluate command on each record') do |cmd|
     options[:eval] = cmd
   end
@@ -37,9 +62,20 @@ opts = OptionParser.new do |o|
     options[:eval_once] = true
     options[:eval] = cmd
   end
+  o.on('--seval cmd',String, 'Evaluate command on each sample') do |cmd|
+    options[:seval] = cmd
+    options[:skip_header] = true
+  end
+  o.on("--rewrite eval", "Rewrite INFO") do |s|
+    options[:rewrite] = s
+  end
+  o.on("--samples list", Array, "Output selected samples") do |l|
+    options[:samples] = l
+  end
   o.on("--rdf", "Generate Turtle RDF") do |b|
     require 'bio-vcf/vcfrdf'
     options[:rdf] = true
+    options[:skip_header] = true
   end
   o.on_tail("--id name", String, "Identifier") do |s|
     options[:id] = s
@@ -62,11 +98,11 @@ opts = OptionParser.new do |o|
     # Bio::Log::CLI.trace('error')
     options[:quiet] = true
   end
-  # 
-  # o.on("-v", "--verbose", "Run verbosely") do |v|
-  #   Bio::Log::CLI.trace('info')
-  # end
-  # 
+   
+  o.on("-v", "--verbose", "Run verbosely") do |v|
+    options[:verbose] = true
+  end
+  
   # o.on("--debug", "Show debug messages") do |v|
   #   Bio::Log::CLI.trace('debug')
   # end
@@ -77,61 +113,158 @@ opts = OptionParser.new do |o|
   end
 end
 
-include BioVcf
 
-begin
-  opts.parse!(ARGV)
+def parse_line line,header,options,samples
+  # fields = VcfLine.parse(line,header.columns)
+  fields = VcfLine.parse(line)
+  rec = VcfRecord.new(fields,header)
+  r = rec # alias
 
-  $stderr.print "vcf #{version} (biogem Ruby #{RUBY_VERSION}) by Pjotr Prins 2014\n" if !options[:quiet]
+  filter = options[:filter]
+  sfilter = options[:sfilter]
+  efilter = options[:efilter]
+  ifilter = options[:ifilter]
+  ignore_missing = options[:ignore_missing]
+  quiet = options[:quiet]
+  # --------------------------
+  # Filtering and set analysis
+  return if filter and not rec.eval(filter,ignore_missing,quiet)
+  
+  if sfilter
+    rec.each_sample(options[:sfilter_samples]) do | sample |
+      return if not sample.eval(sfilter,ignore_missing,quiet)
+    end
+  end
 
-  if options[:show_help] 
-    print opts 
-    print USAGE
-    exit 1
+  if ifilter
+    rec.each_sample(options[:ifilter_samples]) do | sample |
+      return if not sample.eval(ifilter,ignore_missing,quiet)
+    end
+  end
+
+  if efilter
+    rec.each_sample(options[:efilter_samples]) do | sample |
+      return if not sample.eval(efilter,ignore_missing,quiet)
+    end
   end
 
-  $stderr.print "Options: ",options,"\n" if !options[:quiet]
+  # -----------------------------
+  # From here on decide on output
+  if samples
+    # Select certain samples for output
+    newfields = fields[0..8]
+    samples.each do |s|
+      newfields << fields[s+9] 
+    end
+    fields = newfields
+  end
+  if options[:eval] or options[:seval]
+    begin
+      results = nil # result string
+      if options[:eval] 
+        res = rec.eval(options[:eval],ignore_missing,quiet)
+        results = res if res
+      end
+      if options[:seval]
+        list = (results ? [] : [rec.chr,rec.pos])
+        rec.each_sample(options[:sfilter_samples]) { | sample |
+          list << sample.eval(options[:seval],ignore_missing,quiet)
+        }
+        results = (results ? results + "\t" : "" ) + list.join("\t")
+      end
+    rescue => e
+      $stderr.print "\nLine: ",line
+      $stderr.print "ERROR evaluating --eval <#{options[:eval]}> #{e.message}\n"
+      raise if options[:verbose]
+      exit 1
+    end
+    print results,"\n" if results
+    exit(1) if options[:eval_once]
+  else
+    if options[:rdf]
+      # Output Turtle RDF
+      if not header_out
+        VcfRdf::header
+        header_out = true
+      end
+      VcfRdf::record(options[:id],rec,options[:tags])
+    elsif options[:rewrite]
+      # Default behaviour prints VCF line, but rewrite info
+      eval(options[:rewrite]) 
+      print (fields[0..6]+[rec.info.to_s]+fields[8..-1]).join("\t"),"\n"
+    else
+      # Default behaviour prints VCF line
+      print fields.join("\t"),"\n"
+    end
+  end
+end
+
+include BioVcf
+
+opts.parse!(ARGV)
 
-  header = VcfHeader.new
-  header_out = false
+$stderr.print "vcf #{version} (biogem Ruby #{RUBY_VERSION}) by Pjotr Prins 2014\n" if !options[:quiet]
 
-  STDIN.each_line do | line |
+if options[:show_help] 
+  print opts 
+  print USAGE
+  exit 1
+end
+
+$stderr.print "Options: ",options,"\n" if !options[:quiet]
+
+if options[:samples]
+  samples = options[:samples].map { |s| s.to_i }
+end
+header = VcfHeader.new
+header_out = false
+line_number=0
+
+STDIN.each_line do | line |
+  line_number += 1
+  $stderr.print '.' if line_number%100_000 == 0 and not options[:quiet]
+  begin
     if line =~ /^##fileformat=/
       # ---- We have a new file header
       header = VcfHeader.new
       header.add(line)
+      print line if not options[:skip_header]
       STDIN.each_line do | headerline |
         if headerline !~ /^#/
           line = headerline
           break # end of header
         end
         header.add(headerline)
-      end
-    end
-    # ---- Parse VCF record line
-    # fields = VcfLine.parse(line,header.columns)
-    fields = VcfLine.parse(line)
-    rec = VcfRecord.new(fields,header)
-    if !options[:filter] or (options[:filter] and eval(options[:filter]))
-      if options[:eval] 
-        print eval(options[:eval]) 
-        exit(1) if options[:eval_once]
-      else
-        if options[:rdf]
-          # Output Turtle RDF
-          if not header_out
-            VcfRdf::header
-            header_out = true
+        if not options[:skip_header]
+          if headerline =~ /^#CHR/
+            selected = header.column_names
+            if samples
+              newfields = selected[0..8]
+              samples.each do |s|
+                newfields << selected[s+9] 
+              end
+              selected = newfields
+            end
+                  
+            print "#",selected.join("\t"),"\n"
+          else
+            print headerline
           end
-          VcfRdf::record(options[:id],rec,options[:tags])
-        else
-          # Default behaviour prints VCF line
-          print fields.join("\t")
         end
       end
-      print "\n"
     end
+    next if line =~ /^##/ # empty file
+    if not options[:efilter_samples] and options[:ifilter_samples]
+      # Create exclude set as a complement of include set
+      options[:efilter_samples] = header.column_names[9..-1].fill{|i|i.to_s}-options[:ifilter_samples]
+    end
+    # ---- Parse VCF record line
+    parse_line line,header,options,samples
+  rescue Exception => e
+    # $stderr.print line
+    $stderr.print e.message,"\n"
+    raise if options[:verbose]
+    exit 1
   end
-
 end
 

data/bio-vcf.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "bio-vcf"
-  s.version = "0.0.2"
+  s.version = "0.0.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Pjotr Prins"]
-  s.date = "2014-03-05"
+  s.date = "2014-05-24"
   s.description = "Smart parser for VCF format"
   s.email = "pjotr.public01@thebird.nl"
   s.executables = ["bio-vcf"]
@@ -27,15 +27,18 @@ Gem::Specification.new do |s|
     "VERSION",
     "bin/bio-vcf",
     "bio-vcf.gemspec",
+    "features/cli.feature",
     "features/diff_count.feature",
     "features/multisample.feature",
     "features/somaticsniper.feature",
     "features/step_definitions/bio-vcf_steps.rb",
+    "features/step_definitions/cli-feature.rb",
     "features/step_definitions/diff_count.rb",
     "features/step_definitions/multisample.rb",
     "features/step_definitions/somaticsniper.rb",
     "features/support/env.rb",
     "lib/bio-vcf.rb",
+    "lib/bio-vcf/utils.rb",
     "lib/bio-vcf/variant.rb",
     "lib/bio-vcf/vcf.rb",
     "lib/bio-vcf/vcfgenotypefield.rb",
@@ -43,8 +46,17 @@ Gem::Specification.new do |s|
     "lib/bio-vcf/vcfline.rb",
     "lib/bio-vcf/vcfrdf.rb",
     "lib/bio-vcf/vcfrecord.rb",
+    "lib/bio-vcf/vcfsample.rb",
+    "test/data/input/dbsnp.vcf",
     "test/data/input/multisample.vcf",
-    "test/data/input/somaticsniper.vcf"
+    "test/data/input/somaticsniper.vcf",
+    "test/data/regression/eval_r.info.dp.ref",
+    "test/data/regression/r.info.dp.ref",
+    "test/data/regression/rewrite.info.sample.ref",
+    "test/data/regression/s.dp.ref",
+    "test/data/regression/seval_s.dp.ref",
+    "test/data/regression/sfilter001.ref",
+    "test/performance/metrics.md"
   ]
   s.homepage = "http://github.com/pjotrp/bioruby-vcf"
   s.licenses = ["MIT"]
@@ -59,15 +71,18 @@ Gem::Specification.new do |s|
       s.add_development_dependency(%q<rspec>, [">= 0"])
       s.add_development_dependency(%q<cucumber>, [">= 0"])
       s.add_development_dependency(%q<jeweler>, [">= 0"])
+      s.add_development_dependency(%q<regressiontest>, [">= 0"])
     else
       s.add_dependency(%q<rspec>, [">= 0"])
       s.add_dependency(%q<cucumber>, [">= 0"])
       s.add_dependency(%q<jeweler>, [">= 0"])
+      s.add_dependency(%q<regressiontest>, [">= 0"])
     end
   else
     s.add_dependency(%q<rspec>, [">= 0"])
     s.add_dependency(%q<cucumber>, [">= 0"])
     s.add_dependency(%q<jeweler>, [">= 0"])
+    s.add_dependency(%q<regressiontest>, [">= 0"])
   end
 end
 

data/features/cli.feature

@@ -0,0 +1,32 @@
+@cli
+Feature: Command-line interface (CLI)
+
+  bio-vcf has a powerful command line interface. Here we regression test features.
+
+  Scenario: Test the info filter using dp
+    Given I have input file(s) named "test/data/input/multisample.vcf"
+    When I execute "./bin/bio-vcf -i --filter 'r.info.dp>100'"
+    Then I expect the named output to match the named output "r.info.dp"
+
+  Scenario: Test the sample filter using dp
+    Given I have input file(s) named "test/data/input/multisample.vcf"
+    When I execute "./bin/bio-vcf -i --sfilter 's.dp>20'"
+    Then I expect the named output to match the named output "s.dp"
+
+  Scenario: Test the info eval using dp
+    Given I have input file(s) named "test/data/input/multisample.vcf"
+    When I execute "./bin/bio-vcf -i --eval 'r.info.dp'"
+    Then I expect the named output to match the named output "eval_r.info.dp"
+
+  Scenario: Test the sample eval using dp
+    Given I have input file(s) named "test/data/input/multisample.vcf"
+    When I execute "./bin/bio-vcf -i --seval 's.dp'"
+    Then I expect the named output to match the named output "seval_s.dp"
+
+  Scenario: Rewrite an info field
+    Given I have input file(s) named "test/data/input/multisample.vcf"
+    When I execute "./bin/bio-vcf --rewrite rec.info[\'sample\']=\'XXXXX\'"
+    Then I expect the named output to match the named output "rewrite.info.sample"
+
+  
+

data/features/multisample.feature

@@ -8,7 +8,7 @@ Feature: Multi-sample VCF
 
     Given the multi sample header line
     """
-#CHROM  POS     ID      REF     ALT     QUAL    FILTER  INFO    FORMAT  BIOPSY17513D    clone10 clone3  clone4  subclone105     subclone33      subclone46
+#CHROM  POS     ID      REF     ALT     QUAL    FILTER  INFO    FORMAT  Original	s1t1	s2t1	s3t1	s1t2	s2t2	s3t2
     """
     When I parse the header
     Given multisample vcf line
@@ -16,6 +16,7 @@ Feature: Multi-sample VCF
 1       10321   .       C       T       106.30  .       AC=5;AF=0.357;AN=14;BaseQRankSum=3.045;DP=1537;Dels=0.01;FS=5.835;HaplotypeScore=220.1531;MLEAC=5;MLEAF=0.357;MQ=26.69;MQ0=258;MQRankSum=-4.870;QD=0.10;ReadPosRankSum=0.815    GT:AD:DP:GQ:PL  0/1:189,25:218:30:30,0,810      0/0:219,22:246:24:0,24,593      0/1:218,27:248:34:34,0,1134     0/0:220,22:248:56:0,56,1207     0/1:168,23:193:19:19,0,493      0/1:139,22:164:46:46,0,689      0/1:167,26:196:20:20,0,522    
     """
     When I parse the record
+    Then I expect rec.valid? to be true
     Then I expect rec.chrom to contain "1"
     Then I expect rec.pos to contain 10321
     Then I expect rec.ref to contain "C"
@@ -25,13 +26,30 @@ Feature: Multi-sample VCF
     And I expect rec.info.af to be 0.357
     And I expect rec.info.dp to be 1537
     And I expect rec.info.readposranksum to be 0.815
-    And I expect rec.sample['BIOPSY17513D'].gt to be "0/1"
-    And I expect rec.sample['BIOPSY17513D'].ad to be [189,25]
-    And I expect rec.sample['subclone46'].ad to be [167,26]
-    And I expect rec.sample['subclone46'].dp to be 196 
-    And I expect rec.sample['subclone46'].gq to be 20
-    And I expect rec.sample['subclone46'].pl to be [20,0,522]
+    And I expect rec.sample['Original'].ad to be [189,25]
+    And I expect rec.sample['Original'].gt to be [0,1]
+    And I expect rec.sample['s3t2'].ad to be [167,26]
+    And I expect rec.sample['s3t2'].dp to be 196 
+    And I expect rec.sample['s3t2'].gq to be 20
+    And I expect rec.sample['s3t2'].pl to be [20,0,522]
     # And the nicer self resolving
-    And I expect rec.sample.biopsy17513d.gt to be [0,1]
-    And I expect rec.sample.subclone46.pl to be [20,0,522]
-   
+    And I expect rec.sample.original.gt to be [0,1]
+    And I expect rec.sample.s3t2.pl to be [20,0,522]
+    # And the even better
+    And I expect rec.original.gt to be [0,1]
+    And I expect rec.s3t2.pl to be [20,0,522]
+    # Check for missing data
+    And I expect test rec.missing_samples? to be false 
+    And I expect test rec.original? to be true
+    Given multisample vcf line
+    """
+1 10723 . C G 73.85 . AC=4;AF=0.667;AN=6;BaseQRankSum=1.300;DP=18;Dels=0.00;FS=3.680;HaplotypeScore=0.0000;MLEAC=4;MLEAF=0.667;MQ=20.49;MQ0=11;MQRankSum=1.754;QD=8.21;ReadPosRankSum=0.000 GT:AD:DP:GQ:PL  ./. ./. 1/1:2,2:4:6:66,6,0  1/1:4,1:5:3:36,3,0  ./. ./.  0/0:6,0:6:3:0,3,33
+    """
+    When I parse the record
+    Then I expect rec.pos to contain 10723
+    Then I expect rec.valid? to be true
+    And I expect rec.original? to be false
+    And I expect rec.sample.s1t1? to be false
+    And I expect rec.sample.s3t2? to be true
+    And I expect rec.missing_samples? to be true
+

data/features/step_definitions/cli-feature.rb

@@ -0,0 +1,12 @@
+
+Given /^I have input file\(s\) named "(.*?)"$/ do |arg1|
+  @filenames = arg1.split(/,/)
+end
+
+When /^I execute "(.*?)"$/ do |arg1|
+  @cmd = arg1 + ' < ' + @filenames[0]
+end
+
+Then(/^I expect the named output to match the named output "(.*?)"$/) do |arg1|
+  RegressionTest::CliExec::exec(@cmd,arg1).should be_true
+end

data/features/step_definitions/multisample.rb

@@ -6,7 +6,7 @@ end
 When(/^I parse the header$/) do
   expect(@header.column_names.size).to eq 16
   expect(@header.samples.size).to eq 7
-  expect(@header.samples).to eq ["BIOPSY17513D", "clone10", "clone3", "clone4", "subclone105", "subclone33", "subclone46"]
+  expect(@header.samples).to eq ["Original", "s1t1", "s2t1", "s3t1", "s1t2", "s2t2", "s3t2"]
 end
 
 Given(/^multisample vcf line$/) do |string|
@@ -37,37 +37,83 @@ Then(/^I expect rec\.info\.readposranksum to be (\d+)\.(\d+)$/) do |arg1, arg2|
   expect(@rec1.info.readposranksum).to eq 0.815
 end
 
-Then(/^I expect rec\.sample\['BIOPSY(\d+)D'\]\.gt to be "(.*?)"$/) do |arg1, arg2|
-  # p @rec1.sample
-  expect(@rec1.sample['BIOPSY17513D'].gt).to eq "0/1"
+Then(/^I expect rec\.sample\['Original'\]\.gt to be "(.*?)"$/) do |arg1|
+  expect(@rec1.sample['Original'].gt).to eq "0/1"
 end
 
-Then(/^I expect rec\.sample\['BIOPSY(\d+)D'\]\.ad to be \[(\d+),(\d+)\]$/) do |arg1, arg2, arg3|
-  expect(@rec1.sample['BIOPSY17513D'].ad).to eq [189,25]
+Then(/^I expect rec\.sample\['Original'\]\.ad to be \[(\d+),(\d+)\]$/) do |arg1, arg2|
+  expect(@rec1.sample['Original'].ad).to eq [189,25]
 end
 
-Then(/^I expect rec\.sample\['subclone(\d+)'\]\.ad to be \[(\d+),(\d+)\]$/) do |arg1, arg2, arg3|
-  expect(@rec1.sample['subclone46'].ad).to eq [167,26]
+Then(/^I expect rec\.sample\['Original'\]\.gt to be \[(\d+),(\d+)\]$/) do |arg1, arg2|
+  expect(@rec1.sample['Original'].gt).to eq "0/1"
 end
 
-Then(/^I expect rec\.sample\['subclone(\d+)'\]\.dp to be (\d+)$/) do |arg1, arg2|
-  expect(@rec1.sample['subclone46'].dp).to eq 196
+Then(/^I expect rec\.sample\['s(\d+)t(\d+)'\]\.ad to be \[(\d+),(\d+)\]$/) do |arg1, arg2, arg3, arg4|
+  expect(@rec1.sample['s3t2'].ad).to eq [167,26]
 end
 
-Then(/^I expect rec\.sample\['subclone(\d+)'\]\.gq to be (\d+)$/) do |arg1, arg2|
-  expect(@rec1.sample['subclone46'].gq).to eq 20 
+Then(/^I expect rec\.sample\['s(\d+)t(\d+)'\]\.dp to be (\d+)$/) do |arg1, arg2, arg3|
+  expect(@rec1.sample['s3t2'].dp).to eq 196
 end
 
-Then(/^I expect rec\.sample\['subclone(\d+)'\]\.pl to be \[(\d+),(\d+),(\d+)\]$/) do |arg1, arg2, arg3, arg4|
-  expect(@rec1.sample['subclone46'].pl).to eq [20,0,522]
+Then(/^I expect rec\.sample\['s(\d+)t(\d+)'\]\.gq to be (\d+)$/) do |arg1, arg2, arg3|
+  expect(@rec1.sample['s3t2'].gq).to eq 20
 end
 
-Then(/^I expect rec\.sample\.biopsy(\d+)d\.gt to be \[(\d+),(\d+)\]$/) do |arg1, arg2, arg3|
-  expect(@rec1.sample.biopsy17513d.gt).to eq "0/1"
+Then(/^I expect rec\.sample\['s(\d+)t(\d+)'\]\.pl to be \[(\d+),(\d+),(\d+)\]$/) do |arg1, arg2, arg3, arg4, arg5|
+  expect(@rec1.sample['s3t2'].pl).to eq [20,0,522]
 end
 
-Then(/^I expect rec\.sample\.subclone(\d+)\.pl to be \[(\d+),(\d+),(\d+)\]$/) do |arg1, arg2, arg3, arg4|
-  expect(@rec1.sample.subclone46.pl).to eq [20,0,522]
+Then(/^I expect rec\.sample\.original\.gt to be \[(\d+),(\d+)\]$/) do |arg1, arg2|
+  expect(@rec1.sample.original.gt).to eq "0/1"
 end
 
+Then(/^I expect rec\.sample\.s(\d+)t(\d+)\.pl to be \[(\d+),(\d+),(\d+)\]$/) do |arg1, arg2, arg3, arg4, arg5|
+  expect(@rec1.sample.s3t2.pl).to eq [20,0,522]
+end
+
+Then(/^I expect rec\.original\.gt to be \[(\d+),(\d+)\]$/) do |arg1, arg2|
+  expect(@rec1.original.gt).to eq "0/1"
+end
+
+Then(/^I expect rec\.s(\d+)t(\d+)\.pl to be \[(\d+),(\d+),(\d+)\]$/) do |arg1, arg2, arg3, arg4, arg5|
+  expect(@rec1.s3t2.pl).to eq [20,0,522]
+end
+
+Then(/^I expect test rec\.missing_samples\? to be false$/) do
+  expect(@rec1.missing_samples?).to be false
+end
+
+Then(/^I expect test rec\.original\? to be true$/) do
+  expect(@rec1.original?).to be true
+end
+
+Then(/^I expect rec\.missing_samples\? to be true$/) do
+  expect(@rec1.missing_samples?).to be true
+end
+
+Then(/^I expect rec\.original\? to be true$/) do
+  expect(@rec1.original?).to be true
+end
+
+Given(/^multisample vcf line with missing data$/) do |string|
+  pending # express the regexp above with the code you wish you had
+end
+
+Then(/^I expect rec\.original\? to be false$/) do
+  expect(@rec1.original?).to eq false
+end
+
+Then(/^I expect rec\.sample\.s(\d+)t(\d+)\? to be false$/) do |arg1, arg2|
+  expect(@rec1.sample.s1t1?).to eq false
+end
+
+Then(/^I expect rec\.sample\.s(\d+)t(\d+)\? to be true$/) do |arg1, arg2|
+  expect(@rec1.sample.s3t2?).to eq true
+end
+
+Then(/^I expect rec\.valid\? to be true$/) do
+  expect(@rec1.valid?).to eq true
+end